{"id":"https://openalex.org/W2250189593","doi":"https://doi.org/10.3115/v1/p15-4003","title":"In-tool Learning for Selective Manual Annotation in Large Corpora","display_name":"In-tool Learning for Selective Manual Annotation in Large Corpora","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2250189593","doi":"https://doi.org/10.3115/v1/p15-4003","mag":"2250189593"},"language":"en","primary_location":{"id":"doi:10.3115/v1/p15-4003","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p15-4003","pdf_url":"https://aclanthology.org/P15-4003.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of ACL-IJCNLP 2015 System Demonstrations","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/P15-4003.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084843622","display_name":"Erik-L\u00e2n Do Dinh","orcid":"https://orcid.org/0000-0002-1536-3854"},"institutions":[{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"id":"https://openalex.org/I4210102840","display_name":"Ubiquitous Energy (United States)","ror":"https://ror.org/01b06j989","country_code":"US","type":"company","lineage":["https://openalex.org/I4210102840"]}],"countries":["DE","US"],"is_corresponding":true,"raw_author_name":"Erik-L\u00e2n Do Dinh","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab (UKP-TUDA) Department of Computer Science, Technische Universit\u00e4t Darmstadt"],"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP-TUDA) Department of Computer Science, Technische Universit\u00e4t Darmstadt","institution_ids":["https://openalex.org/I4210102840","https://openalex.org/I31512782"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091796714","display_name":"Richard Eckart de Castilho","orcid":"https://orcid.org/0000-0003-0991-7045"},"institutions":[{"id":"https://openalex.org/I4210102840","display_name":"Ubiquitous Energy (United States)","ror":"https://ror.org/01b06j989","country_code":"US","type":"company","lineage":["https://openalex.org/I4210102840"]},{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Richard Eckart de Castilho","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab (UKP-TUDA) Department of Computer Science, Technische Universitt Darmstadt","Ubiquitous Knowledge Processing Lab (UKP-TUDA) Department of Computer Science, Technische Universit\u00e4t Darmstadt"],"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP-TUDA) Department of Computer Science, Technische Universitt Darmstadt","institution_ids":["https://openalex.org/I4210102840"]},{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP-TUDA) Department of Computer Science, Technische Universit\u00e4t Darmstadt","institution_ids":["https://openalex.org/I4210102840","https://openalex.org/I31512782"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027450194","display_name":"Iryna Gurevych","orcid":"https://orcid.org/0000-0003-2187-7621"},"institutions":[{"id":"https://openalex.org/I4210138519","display_name":"DIPF | Leibniz Institute for Research and Information in Education","ror":"https://ror.org/0327sr118","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I4210138519"]},{"id":"https://openalex.org/I31512782","display_name":"Technical University of Darmstadt","ror":"https://ror.org/05n911h24","country_code":"DE","type":"education","lineage":["https://openalex.org/I31512782"]},{"id":"https://openalex.org/I4210102840","display_name":"Ubiquitous Energy (United States)","ror":"https://ror.org/01b06j989","country_code":"US","type":"company","lineage":["https://openalex.org/I4210102840"]}],"countries":["DE","US"],"is_corresponding":false,"raw_author_name":"Iryna Gurevych","raw_affiliation_strings":["Ubiquitous Knowledge Processing Lab (UKP-DIPF) German Institute for Educational Research and Educational Information","Ubiquitous Knowledge Processing Lab (UKP-TUDA) Department of Computer Science, Technische Universitt Darmstadt","Ubiquitous Knowledge Processing Lab (UKP-TUDA) Department of Computer Science, Technische Universit\u00e4t Darmstadt"],"affiliations":[{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP-DIPF) German Institute for Educational Research and Educational Information","institution_ids":["https://openalex.org/I4210138519"]},{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP-TUDA) Department of Computer Science, Technische Universitt Darmstadt","institution_ids":["https://openalex.org/I4210102840"]},{"raw_affiliation_string":"Ubiquitous Knowledge Processing Lab (UKP-TUDA) Department of Computer Science, Technische Universit\u00e4t Darmstadt","institution_ids":["https://openalex.org/I4210102840","https://openalex.org/I31512782"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5084843622"],"corresponding_institution_ids":["https://openalex.org/I31512782","https://openalex.org/I4210102840"],"apc_list":null,"apc_paid":null,"fwci":0.4451,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78154354,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"13","last_page":"18"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8323686122894287},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.8092411160469055},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6580461263656616},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6137012243270874},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5617210865020752},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5152723789215088},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.506393551826477},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.4795351028442383},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.47950512170791626},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4789050817489624},{"id":"https://openalex.org/keywords/recall","display_name":"Recall","score":0.430072546005249},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3974776566028595},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37241339683532715}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8323686122894287},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.8092411160469055},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6580461263656616},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6137012243270874},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5617210865020752},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5152723789215088},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.506393551826477},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.4795351028442383},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.47950512170791626},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4789050817489624},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.430072546005249},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3974776566028595},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37241339683532715},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3115/v1/p15-4003","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p15-4003","pdf_url":"https://aclanthology.org/P15-4003.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of ACL-IJCNLP 2015 System Demonstrations","raw_type":"proceedings-article"},{"id":"pmh:oai:tubiblio.ulb.tu-darmstadt.de:104627","is_oa":false,"landing_page_url":"http://tubiblio.ulb.tu-darmstadt.de/104627/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196390","display_name":"TUbilio (Technical University of Darmstadt)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I31512782","host_organization_name":"Technische Universit\u00e4t Darmstadt","host_organization_lineage":["https://openalex.org/I31512782"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Konferenzver\u00f6ffentlichung"}],"best_oa_location":{"id":"doi:10.3115/v1/p15-4003","is_oa":true,"landing_page_url":"https://doi.org/10.3115/v1/p15-4003","pdf_url":"https://aclanthology.org/P15-4003.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of ACL-IJCNLP 2015 System Demonstrations","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7099999785423279}],"awards":[{"id":"https://openalex.org/G1318222655","display_name":null,"funder_award_id":"Lichtenberg-Professorship","funder_id":"https://openalex.org/F4320320882","funder_display_name":"Volkswagen Foundation"},{"id":"https://openalex.org/G348198870","display_name":null,"funder_award_id":"82806","funder_id":"https://openalex.org/F4320320882","funder_display_name":"Volkswagen Foundation"},{"id":"https://openalex.org/G352791218","display_name":null,"funder_award_id":"(BMBF)","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"},{"id":"https://openalex.org/G6467963393","display_name":null,"funder_award_id":"I/82806","funder_id":"https://openalex.org/F4320320882","funder_display_name":"Volkswagen Foundation"},{"id":"https://openalex.org/G7376894374","display_name":null,"funder_award_id":"01UG1416B","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320320882","display_name":"Volkswagen Foundation","ror":"https://ror.org/03bsmfz84"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2250189593.pdf","grobid_xml":"https://content.openalex.org/works/W2250189593.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W224064951","https://openalex.org/W1574862351","https://openalex.org/W1600481763","https://openalex.org/W2007639625","https://openalex.org/W2013833248","https://openalex.org/W2097606805","https://openalex.org/W2108126316","https://openalex.org/W2109378394","https://openalex.org/W2155241375","https://openalex.org/W2251026067","https://openalex.org/W2251991755","https://openalex.org/W4301420590"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2358294942","https://openalex.org/W2405355225","https://openalex.org/W4367460280","https://openalex.org/W4301519770"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,47,55,61,131],"novel":[3],"approach":[4,59],"to":[5,22,64],"the":[6,13,34,39,66,72,79,87,109,114,117],"selective":[7],"annotation":[8,136],"of":[9,15,26,41,82,86],"large":[10],"corpora":[11],"through":[12],"use":[14,40],"machine":[16],"learning.":[17],"Linguistic":[18],"search":[19,35,67,134],"engines":[20],"used":[21,63],"locate":[23],"potential":[24,81],"instances":[25],"an":[27,84,100],"infrequent":[28],"phenomenon":[29,88],"do":[30],"not":[31],"support":[32],"ranking":[33],"results.":[36],"This":[37],"favors":[38],"high-precision":[42],"queries":[43,52],"that":[44,53],"return":[45],"only":[46,107],"few":[48],"results":[49,68,77],"over":[50],"broader":[51],"have":[54],"higher":[56],"recall.":[57],"Our":[58],"introduces":[60],"classifier":[62,96],"rank":[65],"and":[69,135],"thus":[70],"helping":[71],"annotator":[73],"focus":[74],"on":[75,108],"those":[76],"with":[78],"highest":[80],"being":[83],"instance":[85],"in":[89,92,99,116],"question,":[90],"even":[91],"low-precision":[93],"queries.":[94],"The":[95],"is":[97],"trained":[98],"in-tool":[101],"fashion,":[102],"except":[103],"for":[104],"preprocessing":[105],"relying":[106],"manual":[110],"annotations":[111],"done":[112],"by":[113],"users":[115],"querying":[118],"tool":[119],"itself.":[120],"To":[121],"implement":[122],"this":[123],"approach,":[124],"we":[125],"build":[126],"upon":[127],"CSniper":[128],"1":[129],",":[130],"web-based":[132],"multi-user":[133],"tool.":[137]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}